跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 12 天前AI 評分37

市場條件化 JEPA:從不可預測的市場衝擊中學習

Market-Conditioned JEPA: Learning from Unpredictable Market Shocks

AI 導讀

MC-JEPA 以留一法市場因子作為條件,改善金融時間序列預測。在 11 年的中國 A 股分鐘級數據上,它在涵蓋回報、市場暴露、風險及流動性的九項預測目標中優於 per-asset JEPA。MC-JEPA 在所有流動性目標及 2 小時至 5 天的回報預測中取得最佳 RankIC,歷史回測的投資組合表現亦最佳。

正文

Published on Nov 10

Authors:

,

,

,

,

Abstract

A market-conditioned joint-embedding predictive architecture improves financial time-series prediction by conditioning on a leave-one-out market factor, enhancing market exposure, risk, liquidity, and return forecasts.

Much of the variation in financial time series is driven by market-wide shocks that cannot be predicted from an asset's own history. Per-asset self-supervised learning treats this variation as irreducible noise. Under a latent factor model, we show that conditioning prediction on the realized market factor makes the asset's market exposure necessary for optimal prediction, while reducing the noise against which the asset-specific component is learned. Building on this insight, we introduce Market-Conditioned JEPA (MC-JEPA), a joint-embedding predictive architecture for financial time series. During training, we construct a leave-one-out market condition for each asset from the future target embeddings of other assets and incorporate it through factor loadings derived from the asset's own representation. On 11 years of minute-level Chinese A-share data, MC-JEPA improves over per-asset JEPA across nine targets spanning returns, market exposure, risk, and liquidity, with the strongest and most statistically significant gains in exposure, risk, and liquidity. It achieves the best RankIC on all liquidity targets and on return horizons from two hours to five days, outperforming time-series foundation models and self-supervised baselines, and delivers the best portfolio performance in a historical backtest. Ablations show that the return and exposure gains require the condition to be aligned with the realized market movement. After restoring the volatility scale removed by normalization, the predictor's factor loadings rank stocks by market beta nearly as well as a supervised probe, without labels. A synthetic factor-model study with known parameters shows that conditioning improves the recovery of both market exposure and the asset-specific component.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.13572

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.13572 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.13572 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.13572 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co